ESC-技能：情感支持对话中的技能发现与自我进化

摘要

现有的情感支持对话（ESC）系统主要依赖端到端响应生成或粗粒度的策略监督，可解释性有限，且难以支持系统化的技能提升。我们提出ESC-Skills，一个以技能为中心的框架，能够发现并自我演化可执行的情感支持技能。首先，我们将局部支持交互建模为干预单元（IU），该单元捕捉求助者状态、支持干预及响应后情绪变化之间的状态-动作-结果动态。基于从成功与失败的ESC对话中提取的IU，我们构建了ESC-Skills库，该库包含可执行的情感支持技能，涵盖干预指导、适用条件、预期结果及潜在风险。为提升鲁棒性，我们引入一种多画像自我演化优化框架：ESC智能体在SAGE评估下与多样化模拟求助者画像进行交互。通过分析交互轨迹，识别缺失技能、不安全干预及特定画像的失败模式，并基于模拟验证对技能库进行优化。实验结果表明，ESC-Skills在提升响应质量与对话层级情感结果的同时，提供了更具可解释性与可控性的支持行为。我们将于https://github.com/aliyun/qwen-dianjin 公开代码、提示词及ESC-Skills库。

English

Existing emotional support conversation (ESC) systems mainly rely on end-to-end response generation or coarse strategy supervision, offering limited interpretability and little support for systematic skill improvement. We propose ESC-Skills, a skill-centric framework that discovers and self-evolves executable emotional support skills. We first model localized support interactions as Intervention Units (IUs), which capture state--action--outcome dynamics between seeker states, support interventions, and post-response emotional changes. Based on IUs extracted from both successful and failed ESC dialogues, we construct the ESC-Skills Bank, a repository of executable emotional support skills containing intervention guidance, applicability conditions, expected outcomes, and potential risks. To further improve robustness, we introduce a multi-profile self-evolutionary refinement framework in which an ESC agent interacts with diverse simulated seeker profiles under SAGE evaluation. The resulting interaction traces are analyzed to identify missing skills, unsafe interventions, and profile-specific failure patterns, which are then used to refine the Skills Bank through simulation-based verification. Experimental results demonstrate that ESC-Skills improves both response-level quality and dialogue-level emotional outcomes while providing more interpretable and controllable support behaviors. We will release the code, prompts, and ESC-Skills Bank at https://github.com/aliyun/qwen-dianjin.